# Deepseek Coder v2 vs Qwen3.6 35B-A3B

> Qwen3.6 35B-A3B is the stronger model overall, scoring 37.2 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen3-6-35b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.4 to 31.7.

## Snapshot

| | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 37.2 |
| Rank | 217 | 194 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $1.49 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Qwen3.6 35B-A3B: 36.7 (#190)

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| SciCode | — | 35.8% |
| WeirdML | — | 34.5% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- Qwen3.6 35B-A3B: 21.9 (#126)

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| Terminal-Bench | — | 23% |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Qwen3.6 35B-A3B: 27.2 (#112)

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| NYT Connections (extended) | — | 41.6% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 26% |
| LMArena Hard Prompts | 1207 | — |
| Mystery Game Puzzles | — | 22% |
| DTBench | — | 73.9% |
| LMCA | — | 29.7% |
| Surface Evolver Bench | — | 44.4% |
| Epoch Capabilities Index | — | 143.92 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Qwen3.6 35B-A3B: 37.9 (#90)

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 20.4% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Qwen3.6 35B-A3B: 51.4 (#63)

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| GPQA Diamond | — | 84.8% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Qwen3.6 35B-A3B: —

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Qwen3.6 35B-A3B: —

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1180 | — |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Qwen3.6 35B-A3B: —

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1219 | — |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Qwen3.6 35B-A3B: —

| Benchmark | Deepseek Coder v2 | Qwen3.6 35B-A3B |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1176 | — |

## FAQ

### Is Deepseek Coder v2 better than Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B is the stronger model overall, scoring 37.2 to 35.3 on the Noometry Index.

### Is Deepseek Coder v2 or Qwen3.6 35B-A3B better for coding?

They score almost the same on coding (37.5 vs 36.7); test both on your own repository before choosing.

### How many benchmarks do Deepseek Coder v2 and Qwen3.6 35B-A3B share?

0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.6 35B-A3B has 14.